CN111537841B - Optimization method and system suitable for ground fault type identification - Google Patents
Optimization method and system suitable for ground fault type identification Download PDFInfo
- Publication number
- CN111537841B CN111537841B CN202010614170.4A CN202010614170A CN111537841B CN 111537841 B CN111537841 B CN 111537841B CN 202010614170 A CN202010614170 A CN 202010614170A CN 111537841 B CN111537841 B CN 111537841B
- Authority
- CN
- China
- Prior art keywords
- optimization
- fault
- ground fault
- data
- distribution network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/086—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution networks, i.e. with interconnected conductors
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/50—Testing of electric apparatus, lines, cables or components for short-circuits, continuity, leakage current or incorrect line connections
- G01R31/52—Testing for short-circuits, leakage current or ground faults
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Theoretical Computer Science (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses an optimization method and system suitable for ground fault type identification, which comprises the steps of collecting relevant data of a power distribution network ground fault to carry out normalization processing to form a sample data set; screening out key factors influencing the occurrence of the ground fault of the power distribution network from the sample data set by utilizing a deep learning strategy as influence factors; defining a ground resistance steady-state effective value as a constraint parameter by combining a multi-objective optimization strategy; constructing an optimization model based on a binary linear programming strategy, and inputting the influence factors and the constraint parameters for optimization training; and analyzing the type of the distribution network ground fault to be detected by using the trained optimization model, and outputting an optimized analysis result. The invention improves the identification accuracy, reduces the fault maintenance cost, does not need manual operation, and avoids the problems of manual error and potential safety hazard of external invasion.
Description
Technical Field
The invention relates to the technical field of distribution network fault identification and target optimization, in particular to an optimization method and system suitable for ground fault type identification.
Background
Under the background of automatic upgrading of the existing power grid equipment, the cost of the matched monitoring equipment of the power distribution network is continuously reduced, the monitoring means of the operation and fault information of the power distribution network is continuously enriched and perfected, and the requirement for guaranteeing the normal operation of the power distribution network from a unified and global level is difficult to meet by means of a single equipment monitoring method. With the construction of smart power grids in China, the requirements of China and users on power supply reliability are higher and higher, the reliability of power supply in China is up to 99.82% by 2020, and the distribution network line faults account for the vast majority of power failure faults of users, so that timely and rapid positioning and processing of the distribution network line faults are important means for achieving the purposes. The method has the advantages that fault reasons are identified from the running information of the power grid, system logs are formed for the fault reasons, line maintenance and operation are carried out aiming at fault conditions by analyzing the occurrence frequency of the data information, the severity of each fault and other data information, richer information can be provided for safety maintenance and running of the power distribution network, further defense is established from the main source of causing power grid accidents, the important guarantee of the running reliability target of the power distribution network can be improved, and the method has very important significance for improving the safe running reliability of the power grid.
In recent years, the transient method-based distribution network line fault location technology greatly improves the adaptability to single-phase earth faults, but can only locate the faults to a section, which brings certain difficulty to troubleshooting of fault points, and if the fault types can be further judged according to fault monitoring waveforms, richer and more detailed fault information is provided for fault line patrollers, so that the fault troubleshooting efficiency can be greatly improved; the existing fault identification technology is immature and cannot achieve good identification accuracy, and although various existing intelligent means are related to distribution network fault identification and inspection application, the realized economic cost is too high, the labor demand is large, the operation is complicated and the fault is easy to make mistakes, so that an analysis application method aiming at distribution network fault identification is needed to ensure that the identification accuracy is improved, the economic cost is reduced and the phenomenon of manual operation fault is avoided.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned conventional problems.
Therefore, the invention provides an optimization method and system suitable for ground fault type identification, which can reduce the cost of distribution network fault maintenance and improve the identification accuracy.
In order to solve the technical problems, the invention provides the following technical scheme: acquiring relevant data of the power distribution network ground fault to perform normalization processing to form a sample data set; screening out key factors influencing the occurrence of the ground fault of the power distribution network from the sample data set by utilizing a deep learning strategy as influence factors; defining a ground resistance steady-state effective value as a constraint parameter by combining a multi-objective optimization strategy; constructing an optimization model based on a binary linear programming strategy, and inputting the influence factors and the constraint parameters for optimization training; and analyzing the type of the distribution network ground fault to be detected by using the trained optimization model, and outputting an optimized analysis result.
As a preferred embodiment of the optimization method for identifying the type of the ground fault according to the present invention, wherein: constructing the optimization model, including constructing the optimization model using the binary linear programming strategy, as follows,
Zab≤Sab,a＝1,2,…,A，xma∈{0,1}
wherein, A: the number of sampling points in the sample data set, B: the number of time periods during which each fault type occurs in the sample data set,
each detection request can only select one sampling point for detection, Sab: sampling point detection supplyMatrix rmb: sampling point detection requirement matrix, xma: sample point selection matrix, Zab: sampling point fault detection matrix, S: the influence factor, t: the constraint parameter.
As a preferred embodiment of the optimization method for identifying the type of the ground fault according to the present invention, wherein: the optimization training comprises initializing the influence factors and the constraint parameters, and inputting a training set to train the optimization model; calling the written multi-objective optimization strategy to autonomously set an optimization threshold, and if the optimization model does not meet the threshold requirement, performing assignment optimization on the influence factors and the constraint parameters according to errors until the data precision of the test set meets the threshold requirement; and the optimization model outputs a decision and compares data results recorded by the verification set, and if the results are consistent, the training of the optimization model is finished.
As a preferred embodiment of the optimization method for identifying the type of the ground fault according to the present invention, wherein: further comprising, when B is 1, a start time period and when B is B, an end time period; when S isabWhen the sampling point is 1, the sampling point a normally operates in the period b, and SabWhen the value is equal to 0, the fault occurs; when r ismbWhen 1, the m detection request stops in the b time period, rmbWhen the value is equal to 0, detecting the fault; when x ismaThe sample point which is finally numbered a for the mth test request when 1 receives a match, xmaWhen the value is 0, the detection request is refused to be accepted; when Z isab1 is detected for the a-th sampling point in the k-th time period, ZabWhen 0, the state is not detected.
As a preferred embodiment of the optimization method for identifying the type of the ground fault according to the present invention, wherein: the influence factors comprise failure frequency, failure recovery time, natural environment, geographical conditions, insufficient failure monitoring equipment, deficient line information, various line joints, uncertain failure mechanism and medium influence.
As a preferred embodiment of the optimization method for identifying the type of the ground fault according to the present invention, wherein: the constraint parameters comprise that the steady state effective value of the ground resistance is calculated for any fault data in the sample data set by combining fault phase voltage and fault current, as follows,
wherein u isk: the faulty phase voltage ik: said fault current, Rt: and a ground transition resistor.
As a preferred embodiment of the optimization method for identifying the type of the ground fault according to the present invention, wherein: the sample data set comprises a training set, a test set and a verification set which are respectively formed by carrying out normalization processing on the collected data related to the power distribution network ground fault; the training set comprises unit cycle zero sequence current data and fault waveform data in a fault steady state period; the test set comprises data of the type of the ground fault to be detected; the validation set includes identifying statistically good ground fault type data.
As a preferred embodiment of the optimization method for identifying the type of the ground fault according to the present invention, wherein: analyzing the distribution network ground fault type, including identifying arc characteristics in fault zero-sequence current by using an LSTM structure to establish a deep network model so as to distinguish reliable ground faults from unreliable ground faults; taking the reliable grounding fault and the unreliable grounding fault as classification targets, taking a fault resistance effective value sequence as input quantity, and constructing a neural network classification model based on a grounding resistance steady-state effective value; identifying the type of the ground fault by using the neural network classification model, and outputting an identification result; inputting the recognition result into the optimization model for optimization, and initializing the influence factor and the constraint parameter; calculating a parameter loss value in the parameter optimizing process of the optimization model by using a binary classification loss objective function; and the optimization model automatically adjusts the assignment of the influence factors and the constraint parameters according to the parameter loss value until the parameter loss value is minimum, and outputs the analysis result.
As a preferred embodiment of the optimization method for identifying the type of the ground fault according to the present invention, wherein: the analysis result comprises that if the recognition result after optimization is consistent with the recognition result before optimization, the recognition result is directly output; and if the identification result after optimization is inconsistent with the identification result before optimization, outputting the identification result after optimization, and reserving each parameter value during optimization.
As a preferred solution of the optimization system suitable for ground fault type identification according to the present invention, wherein: the system comprises an acquisition module, a data processing module and a data processing module, wherein the acquisition module is used for collecting the relevant data of the power distribution network ground fault and the influence factors and providing sample data for an optimization module; the optimization module is connected with the acquisition module and used for optimizing the recognition result and various parameters, the optimization module comprises an operation unit and an analysis unit, the operation unit is used for calculating various parameters and parameter loss values, carrying out data unified processing and assignment optimization on the influence factors and the constraint parameters, and the analysis unit is used for comparing the recognition result before and after optimization, correcting the optimization parameters of the operation unit and outputting the analysis result; the database is connected with the acquisition module and the optimization module and is used for storing all received data information and providing allocation and supply services for the optimization module; the input and output module is connected with the acquisition module, the optimization module and the database and is used for transmitting various data information and feedback instructions and providing connection channel services for the modules.
The invention has the beneficial effects that: according to the method, the influence factors and the constraint parameters are screened out through the normalization processing of the relevant data of the power distribution network ground fault, so that an optimization model is constructed to optimize the identification result, the loss value is calculated, the identification accuracy is improved, the fault maintenance cost is reduced, manual operation is not needed, and the problems of occurrence of manual errors and potential safety hazards of external invasion are solved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
fig. 1 is a schematic flowchart of an optimization method suitable for identifying a ground fault type according to a first embodiment of the present invention;
fig. 2 is a schematic structural diagram of an LSTM suitable for an optimization method of ground fault type identification according to a first embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating two comparative test output curves of an optimization method for identifying the type of ground fault according to a first embodiment of the present invention;
fig. 4 is a schematic block diagram illustrating a distribution of an optimization system for ground fault type identification according to a second embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, specific embodiments accompanied with figures are described in detail below, and it is apparent that the described embodiments are a part of the embodiments of the present invention, not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those specifically described and will be readily apparent to those of ordinary skill in the art without departing from the spirit of the present invention, and therefore the present invention is not limited to the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Example 1
At present, a power distribution network is still in a working state that fault monitoring equipment is insufficient and line information is deficient, connection points of the power distribution network are numerous, fault mechanisms are unclear, so that a series of problems that low current grounding is difficult to detect, fault positioning technology adaptability is poor and the like still exist.
Referring to fig. 1 to 3, a first embodiment of the present invention provides an optimization method suitable for ground fault type identification, including:
s1: collecting relevant data of the power distribution network ground fault for normalization processing to form a sample data set. It should be noted that the sample data set includes:
carrying out normalization processing on the collected relevant data of the power distribution network ground fault to respectively form a training set, a testing set and a verification set;
the training set comprises unit cycle zero sequence current data and fault waveform data during fault steady state;
the test set comprises data of the type of the ground fault to be detected;
the validation set includes identifying statistically good ground fault type data.
S2: and (4) screening out key factors influencing the occurrence of the ground fault of the power distribution network from the sample data set by utilizing a deep learning strategy as influencing factors. It should be noted in this step that the influencing factors include:
failure frequency, failure recovery time, natural environment, geographical conditions, failure monitoring equipment deficiency, line information deficiency, multiple line contacts, ambiguous failure mechanisms, and medium effects.
S3: and defining the ground resistance steady-state effective value as a constraint parameter by combining a multi-objective optimization strategy. It should be further noted that the constraint parameters include:
the steady state effective value of the grounding resistance is calculated for any fault data in the sample data set by combining the fault phase voltage and the fault current, as follows,
wherein u isk: faulty phase voltage ik: fault current, Rt: and a ground transition resistor.
S4: and constructing an optimization model based on a binary linear programming strategy, and inputting influence factors and constraint parameters for optimization training. It should be further noted that, in this step, the construction of the optimization model includes:
an optimization model is constructed using a binary linear programming strategy, as follows,
Zab≤Sab,a＝1,2,…,A，xma∈{0,1}
wherein, A: sampling point number in sample data set, B: the number of time periods during which each fault type occurs in the sample data set,
each detection request can only select one sampling point for detection, Sab: sampling point detection supply matrix, rmb: sampling point detection requirement matrix, xma: sample point selection matrix, Zab: sampling point fault detection matrix, S: influence factor, t: and (4) constraint parameters.
Specifically, the optimization training comprises:
initializing an influence factor and a constraint parameter, and inputting a training set to train an optimization model;
calling the written multi-objective optimization strategy to autonomously set an optimization threshold, and if the optimization model does not meet the threshold requirement, performing assignment optimization on the influence factors and the constraint parameters according to errors until the data precision of the test set meets the threshold requirement;
and the optimization model outputs a decision and compares data results recorded by the verification set, and if the results are consistent, the training of the optimization model is finished.
Further, the method also comprises the following steps:
a start period when B is 1 and an end period when B is B;
when S isabWhen 1 is equal toThe a-th sampling point normally operates in the b-th time period, SabWhen the value is equal to 0, the fault occurs;
when r ismbWhen 1, the m detection request stops in the b time period, rmbWhen the value is equal to 0, detecting the fault;
when x ismaThe sample point which is finally numbered a for the mth test request when 1 receives a match, xmaWhen the value is 0, the detection request is refused to be accepted;
when Z isab1 is detected for the a-th sampling point in the k-th time period, ZabWhen 0, the state is not detected.
S5: and analyzing the type of the distribution network ground fault to be detected by using the trained optimization model, and outputting an optimized analysis result. It should be further noted that, referring to fig. 2, analyzing the distribution network ground fault type includes:
establishing a deep network model by using an LSTM structure to identify arc characteristics in fault zero-sequence current so as to distinguish reliable earth faults from unreliable earth faults;
taking reliable earth faults and unreliable earth faults as classification targets, taking a fault resistance effective value sequence as input quantity, and constructing a neural network classification model based on the ground resistance steady-state effective value;
identifying the type of the ground fault by using a neural network classification model, and outputting an identification result;
inputting the recognition result into an optimization model for optimization, and initializing an influence factor and a constraint parameter;
calculating a parameter loss value in the parameter optimizing process of the optimization model by using a binary classification loss objective function;
and the optimization model automatically adjusts the assignment of the influence factors and the constraint parameters according to the parameter loss value until the parameter loss value is minimum, and outputs an analysis result.
Further, the analysis result includes:
if the recognition result after optimization is consistent with the recognition result before optimization, directly outputting the recognition result;
and if the optimized recognition result is inconsistent with the recognition result before optimization, outputting the optimized recognition result and reserving each parameter value during optimization.
Preferably, the existing ground faults generally comprise arc light ground faults, metallic ground faults, wet soil ground faults, wet sand ground faults, dry soil ground faults, dry sand ground faults, wet cement ground faults, branch ground faults and water resistance ground faults.
It should be further noted that, in the present embodiment, the existing fault diagnosis parameter identification optimization method tests the node voltage of the electronic circuit by exciting a single power supply, comparing with normal node voltage to obtain node voltage difference, expressing electronic element parameter variation with equivalent power supply to establish circuit characteristic equation, establishing parameter identification equation by using optimization theory and circuit characteristic equation, solving based on penalty function or lagrange multiplier, determining whether a fault occurs according to the parameter variation and the parameter tolerance of the electronic component represented by the equivalent current source or the equivalent voltage source, the method mainly solves the technical problems that the existing fault diagnosis optimization method has huge on-line calculation amount and cannot meet the real-time requirement of modern industry, the method is only suitable for fault maintenance of the power distribution network circuit, and only can optimize the identification speed and cannot improve the accuracy; the existing fault signal detection and waveform identification optimization method is characterized in that a current transformer is used for collecting signal data of an electric power system, the signal data is connected with the data collection card through the transformer and converted into digital signals by the data collection card and sent to an upper computer, the upper computer adopts an optimization algorithm to estimate direct current offset and an estimation initial point of fundamental wave components, harmonic wave components and exponential attenuation of the signals of the electric power system, and reconstructs the signals of the electric power system according to the estimated parameters.
Preferably, in order to better verify and explain the technical effects adopted in the method of the present invention, the embodiment respectively selects the traditional fault diagnosis parameter identification optimization method and the method of the present invention to perform a comparison test, and compares the test results by means of scientific demonstration to verify the real effect of the method of the present invention; in order to verify that the method of the present invention has higher accuracy and lower economic cost compared with the conventional method, the present embodiment respectively performs real-time measurement and comparison on the identification optimization of various ground faults of a certain power distribution network by using the conventional method and the method of the present invention.
And (3) testing conditions are as follows: (1) the network training framework is Tensorflow1.10 and TFLearn, and the programming language is python 3.6;
(2) the fault types are set to be dry soil ground, dry sand ground, branch ground, wet sand ground, wet soil ground, wet cement ground and water resistance ground;
(3) starting automatic test equipment, performing MATLB simulation operation, and obtaining simulation curve data according to an experiment result.
Referring to fig. 3, a solid line is a curve output by the method of the present invention, a dotted line is a curve output by the conventional method, and according to the schematic diagram of fig. 3, it can be seen that the solid line always rises compared to the dotted line, and the distance difference between the solid line and the dotted line is large.
Example 2
Referring to fig. 4, a second embodiment of the present invention, which is different from the first embodiment, provides an optimization system for ground fault type identification, including:
the acquisition module 100 is configured to collect data and impact factors related to the power distribution network ground fault, and provide sample data for the optimization module 200.
The optimization module 200 is connected to the acquisition module 100 and used for optimizing the recognition result and various parameters, the optimization module 200 includes an operation unit 201 and an analysis unit 202, the operation unit 201 is used for calculating various parameters and parameter loss values, performing data unified processing and assignment optimization on the influence factors and the constraint parameters, and the analysis unit 202 is used for comparing the recognition results before and after optimization, checking the optimization parameters of the operation unit 201, and outputting the analysis result.
The database 300 is connected to the collection module 100 and the optimization module 200, and is used for storing all received data information and providing the optimization module 200 with a provisioning service.
The input/output module 400 is connected to the acquisition module 100, the optimization module 200 and the database 300, and is configured to transmit various data information and feedback instructions, and provide a connection channel service for each module.
Preferably, it should be further noted that the optimization module 200 is mainly divided into three layers, including a control layer, an operation layer and a storage layer, where the control layer is a command control center of the optimization module 200 and is composed of an instruction register IR, an instruction decoder ID and an operation controller OC, and the control layer can sequentially fetch each instruction from a memory according to a program pre-programmed by a user, place the instruction in the instruction register IR, analyze and determine the instruction by the instruction decoder, notify the operation controller OC to operate, and send a micro-operation control signal to a corresponding component according to a determined time sequence; the operation layer is the core of the optimization module 200, can perform arithmetic operations (such as addition, subtraction, multiplication, division and addition operations) and logical operations (such as shift, logical test or two-value comparison), is connected to the control layer, and performs operation operations by receiving control signals of the control layer; the storage layer is a database of the optimization module 200, and can store data (both pending and processed).
It should be recognized that embodiments of the present invention can be realized and implemented by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer readable memory. The methods may be implemented in a computer program using standard programming techniques, including a non-transitory computer-readable storage medium configured with the computer program, where the storage medium so configured causes a computer to operate in a specific and predefined manner, according to the methods and figures described in the detailed description. Each program may be implemented in a high level procedural or object oriented programming language to communicate with a computer system. However, the program(s) can be implemented in assembly or machine language, if desired. In any case, the language may be a compiled or interpreted language. Furthermore, the program can be run on a programmed application specific integrated circuit for this purpose.
Further, the operations of processes described herein can be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and/or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) collectively executed on one or more processors, by hardware, or combinations thereof. The computer program includes a plurality of instructions executable by one or more processors.
Further, the method may be implemented in any type of computing platform operatively connected to a suitable interface, including but not limited to a personal computer, mini computer, mainframe, workstation, networked or distributed computing environment, separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, and the like. Aspects of the invention may be embodied in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, optically read and/or write storage medium, RAM, ROM, or the like, such that it may be read by a programmable computer, which when read by the storage medium or device, is operative to configure and operate the computer to perform the procedures described herein. Further, the machine-readable code, or portions thereof, may be transmitted over a wired or wireless network. The invention described herein includes these and other different types of non-transitory computer-readable storage media when such media include instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor. The invention also includes the computer itself when programmed according to the methods and techniques described herein. A computer program can be applied to input data to perform the functions described herein to transform the input data to generate output data that is stored to non-volatile memory. The output information may also be applied to one or more output devices, such as a display. In a preferred embodiment of the invention, the transformed data represents physical and tangible objects, including particular visual depictions of physical and tangible objects produced on a display.
As used in this application, the terms "component," "module," "system," and the like are intended to refer to a computer-related entity, either hardware, firmware, a combination of hardware and software, or software in execution. For example, a component may be, but is not limited to being: a process running on a processor, an object, an executable, a thread of execution, a program, and/or a computer. By way of example, both an application running on a computing device and the computing device can be a component. One or more components can reside within a process and/or thread of execution and a component can be localized on one computer and/or distributed between two or more computers. In addition, these components can execute from various computer readable media having various data structures thereon. The components may communicate by way of local and/or remote processes such as in accordance with a signal having one or more data packets (e.g., data from one component interacting with another component in a local system, distributed system, and/or across a network such as the internet with other systems by way of the signal).
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (6)
1. An optimization method suitable for identifying the type of a ground fault is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
collecting relevant data of the power distribution network ground fault to perform normalization processing to form a sample data set;
screening out key factors influencing the occurrence of the ground fault of the power distribution network from the sample data set by utilizing a deep learning strategy as influence factors;
defining a ground resistance steady-state effective value as a constraint parameter by combining a multi-objective optimization strategy;
constructing an optimization model based on a binary linear programming strategy, and inputting the influence factors and the constraint parameters for optimization training;
analyzing the type of the distribution network ground fault to be detected by using the trained optimization model, and outputting an optimized analysis result;
constructing the optimization model, including,
the optimization model is constructed using the binary linear programming strategy as follows,
Zab≤Sab,a＝1,2,…,A，xma∈{0,1}
wherein, A: the number of sampling points in the sample data set, B: the number of time periods during which each fault type occurs in the sample data set,
each detection request can only select one sampling point for detection, Sab: sampling point detection supply matrix, rmb: sampling point detection requirement matrix, xma: sample point selection matrix, Zab: sampling point fault detection matrix, S: the influence factor, t: the constraint parameter;
the optimization training comprises the steps of,
initializing the influence factors and the constraint parameters, and inputting a training set to train the optimization model;
calling the written multi-objective optimization strategy to autonomously set an optimization threshold, and if the optimization model does not meet the threshold requirement, performing assignment optimization on the influence factors and the constraint parameters according to errors until the data precision of the test set meets the threshold requirement;
the optimization model outputs a decision and compares data results recorded by the verification set, and if the results are consistent, the optimization model training is finished;
also comprises the following steps of (1) preparing,
a start period when B is 1 and an end period when B is B;
when S isabWhen the sampling point is 1, the sampling point a normally operates in the period b, and SabWhen the value is equal to 0, the fault occurs;
when r ismbWhen 1, the m detection request stops in the b time period, rmbWhen the value is equal to 0, detecting the fault;
when x ismaThe sample point which is finally numbered a for the mth test request when 1 receives a match, xmaWhen the value is 0, the detection request is refused to be accepted;
when Z isab1 is detected for the a-th sampling point in the k-th time period, ZabWhen the value is equal to 0, the state is not detected;
the impact factors include, for example,
failure frequency, failure recovery time, natural environment, geographical conditions, failure monitoring equipment deficiencies, lack of line information, numerous line contacts, ambiguous failure mechanisms, or medium effects.
2. Optimization method suitable for ground fault type identification according to claim 1, characterized in that: the constraint parameters may include, for example,
calculating the steady state effective value of the grounding resistance by combining the fault phase voltage and the fault current for any fault data in the sample data set, as follows,
wherein u isk: the faulty phase voltage ik: the fault current, r (t): the ground resistance steady state effective value.
3. Optimization method suitable for ground fault type identification according to claim 2, characterized in that: the set of sample data comprises a set of samples,
carrying out normalization processing on the collected relevant data of the power distribution network ground fault to respectively form the training set, the test set and the verification set;
the training set comprises unit cycle zero sequence current data and fault waveform data in a fault steady state period;
the test set comprises data of the type of the ground fault to be detected;
the validation set includes identifying statistically good ground fault type data.
4. An optimization method suitable for ground fault type identification according to claim 2 or 3, characterized in that: analyzing the distribution network ground fault types, including,
establishing a deep network model by using an LSTM structure to identify arc characteristics in fault zero-sequence current so as to distinguish reliable earth faults from unreliable earth faults;
taking the reliable grounding fault and the unreliable grounding fault as classification targets, taking a fault resistance effective value sequence as input quantity, and constructing a neural network classification model based on a grounding resistance steady-state effective value;
identifying the type of the ground fault by using the neural network classification model, and outputting an identification result;
inputting the recognition result into the optimization model for optimization, and initializing the influence factor and the constraint parameter;
calculating a parameter loss value in the parameter optimizing process of the optimization model by using a binary classification loss objective function;
and the optimization model automatically adjusts the assignment of the influence factors and the constraint parameters according to the parameter loss value until the parameter loss value is minimum, and outputs the analysis result.
5. Optimization method suitable for ground fault type identification according to claim 4, characterized in that: the result of the analysis includes the results of,
if the recognition result after optimization is consistent with the recognition result before optimization, directly outputting the recognition result;
and if the identification result after optimization is inconsistent with the identification result before optimization, outputting the identification result after optimization, and reserving each parameter value during optimization.
6. An optimization system suitable for the optimization method of the ground fault type identification according to claim 5, characterized in that: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
the acquisition module (100) is used for collecting the relevant data of the power distribution network ground fault and the influence factors and providing sample data for the optimization module (200);
the optimization module (200) is connected to the acquisition module (100) and used for optimizing recognition results and various parameters, the optimization module (200) comprises an operation unit (201) and an analysis unit (202), the operation unit (201) is used for calculating various parameters and parameter loss values, data unified processing and assignment optimization are carried out on the influence factors and the constraint parameters, the analysis unit (202) is used for comparing the recognition results before and after optimization, correcting the optimization parameters of the operation unit (201), and outputting the analysis results;
the database (300) is connected with the acquisition module (100) and the optimization module (200) and is used for storing all received data information and providing a deploying and supplying service for the optimization module (200);
the input and output module (400) is connected with the acquisition module (100), the optimization module (200) and the database (300) and is used for transmitting various data information and feedback instructions and providing connection channel services for the modules.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010614170.4A CN111537841B (en) | 2020-06-30 | 2020-06-30 | Optimization method and system suitable for ground fault type identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010614170.4A CN111537841B (en) | 2020-06-30 | 2020-06-30 | Optimization method and system suitable for ground fault type identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111537841A CN111537841A (en) | 2020-08-14 |
| CN111537841B true CN111537841B (en) | 2021-08-06 |
Family
ID=71976516
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010614170.4A Active CN111537841B (en) | 2020-06-30 | 2020-06-30 | Optimization method and system suitable for ground fault type identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111537841B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110082640B (en) * | 2019-05-16 | 2021-11-30 | 国网安徽省电力有限公司 | Distribution network single-phase earth fault identification method based on long-time memory network |
| CN112083275A (en) * | 2020-08-21 | 2020-12-15 | 广东电网有限责任公司广州供电局 | Distribution network fault type identification method and system |
| CN112147462A (en) * | 2020-09-16 | 2020-12-29 | 国网江西省电力有限公司电力科学研究院 | Power transmission line fault identification method based on deep learning |
| CN112541399B (en) * | 2020-11-19 | 2022-11-15 | 山东信通电子股份有限公司 | Transmission line monitoring control method and device |
| CN113609891A (en) * | 2021-06-15 | 2021-11-05 | 北京瞭望神州科技有限公司 | Ship identification monitoring method and system |
| CN114444381A (en) * | 2021-12-30 | 2022-05-06 | 南京诺源医疗器械有限公司 | Control method and system suitable for light source |
| CN114636900B (en) * | 2022-05-11 | 2022-09-30 | 广东电网有限责任公司东莞供电局 | Power distribution network multiple fault diagnosis method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101179195A (en) * | 2007-11-15 | 2008-05-14 | 上海交通大学 | Power distribution network planning scheme assistant decision system |
| CN104091070A (en) * | 2014-07-07 | 2014-10-08 | 北京泰乐德信息技术有限公司 | Rail transit fault diagnosis method and system based on time series analysis |
| CN106059492A (en) * | 2016-05-05 | 2016-10-26 | 江苏方天电力技术有限公司 | Photovoltaic assembly shadow fault type determination method based on power prediction |
| CN107632231A (en) * | 2017-10-30 | 2018-01-26 | 陕西省地方电力设计有限公司 | A kind of grounding net of transformer substation corrosion failure inline diagnosis method using multiple activation source |
| CN110133438A (en) * | 2019-05-16 | 2019-08-16 | 国网安徽省电力有限公司 | A kind of singlephase earth fault discrimination method based on phase space reconfiguration Yu conductance feature |
| CN110348114A (en) * | 2019-07-09 | 2019-10-18 | 电子科技大学 | A kind of non-precision fault recognition method of power grid completeness status information reconstruct |
-
2020
- 2020-06-30 CN CN202010614170.4A patent/CN111537841B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101179195A (en) * | 2007-11-15 | 2008-05-14 | 上海交通大学 | Power distribution network planning scheme assistant decision system |
| CN104091070A (en) * | 2014-07-07 | 2014-10-08 | 北京泰乐德信息技术有限公司 | Rail transit fault diagnosis method and system based on time series analysis |
| CN106059492A (en) * | 2016-05-05 | 2016-10-26 | 江苏方天电力技术有限公司 | Photovoltaic assembly shadow fault type determination method based on power prediction |
| CN107632231A (en) * | 2017-10-30 | 2018-01-26 | 陕西省地方电力设计有限公司 | A kind of grounding net of transformer substation corrosion failure inline diagnosis method using multiple activation source |
| CN110133438A (en) * | 2019-05-16 | 2019-08-16 | 国网安徽省电力有限公司 | A kind of singlephase earth fault discrimination method based on phase space reconfiguration Yu conductance feature |
| CN110348114A (en) * | 2019-07-09 | 2019-10-18 | 电子科技大学 | A kind of non-precision fault recognition method of power grid completeness status information reconstruct |
Non-Patent Citations (3)
| Title |
|---|
| 基于LＳＴＭ模型的配电网单相接地故障辨识方法;邵庆祝 等;《广东电力》;20190930;摘要，第101页第1栏，第103页第1栏，第104页 * |
| 私家车位预订匹配优化模型及计算方法研究;孙智慧 等;《石家庄铁道大学学报》;20191231;第90页 * |
| 邵庆祝 等.基于LＳＴＭ模型的配电网单相接地故障辨识方法.《广东电力》.2019,摘要，第101页第1栏，第103页第1栏，第104页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111537841A (en) | 2020-08-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111537841B (en) | Optimization method and system suitable for ground fault type identification | |
| CN110516837B (en) | AI-based intelligent diagnosis method, system and device | |
| CN111400371A (en) | Voltage correlation verification-based user variable relationship identification method | |
| CN111579936B (en) | Positioning method and system suitable for arc light grounding fault | |
| CN113887846B (en) | Out-of-tolerance risk early warning method for capacitive voltage transformer | |
| CN112039073B (en) | Collaborative optimization method and system suitable for fault judgment of power distribution room equipment | |
| CN112085071A (en) | Power distribution room equipment fault analysis and pre-judgment method and device based on edge calculation | |
| CN113297797A (en) | XGboost-based electronic transformer measurement error state evaluation method and device | |
| CN105719094A (en) | State evaluation method of power transmission equipment | |
| CN108896804A (en) | Stealing detection method, device and electronic equipment | |
| CN116401532B (en) | Method and system for recognizing frequency instability of power system after disturbance | |
| CN112083275A (en) | Distribution network fault type identification method and system | |
| CN113987294A (en) | CVT (continuously variable transmission) online fault diagnosis method based on genetic optimization GRU (generalized regression Unit) neural network | |
| CN116520068A (en) | Diagnostic method, device, equipment and storage medium for electric power data | |
| CN111179576A (en) | Power utilization information acquisition fault diagnosis method and system with inductive learning function | |
| CN111999691A (en) | Error calibration method and error calibration device for metering sensor device | |
| CN115408927B (en) | Data processing method and device for predicting rock mass parameters | |
| CN116975389A (en) | Transformer substation fault analysis method and device | |
| CN112037084B (en) | Method and system for testing fault processing, testing and analyzing of power distribution main station | |
| CN115422821A (en) | Data processing method and device for rock mass parameter prediction | |
| CN115389833A (en) | Automatic capacity checking method for 315kV and below voltage class distribution transformer | |
| CN113988493A (en) | Method and device for constructing terminal evaluation model and storage medium | |
| CN111625525A (en) | Environmental data repairing/filling method and system | |
| CN110426752A (en) | A kind of reservoir parameter inversion method and system based on petrophysical model | |
| CN116627759B (en) | Financial payment equipment circuit safety detection device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |